计算机科学技术学报 ›› 2019,Vol. 34 ›› Issue (1): 47-60.doi: 10.1007/s11390-019-1898-8

所属专题： Artificial Intelligence and Pattern Recognition

• • 上一篇    下一篇

基于人脸去识别的隐私保护对抗生成网络

Yifan Wu1, Fan Yang1, Yong Xu2, Senior Member, CCF, ACM, IEEE, and Haibin Ling1, Senior Member, IEEE   

  1. 1 Department of Computer and Information Sciences, Temple University, Philadelphia 19122, U.S.A.;
    2 School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China
  • 收稿日期:2018-07-12 修回日期:2018-12-20 出版日期:2019-01-05 发布日期:2019-01-12
  • 作者简介:Yifan Wu received her B.S. degree in communication engineering from China University of Geosciences, Wuhan, and M.S. degree in computer science from Temple University, Philadelphia, in 2016 and 2017, respectively. She is currently a Ph.D. student in bioengineering at University of Pennsylvania, Philadelphia. Her current research interests are computer vision and medical image processing.
  • 基金资助:
    This work was supported by the National Natural Science Foundation of China under Grant No. 61528204, and the National Science Foundation of USA under Grant No. 1350521.

Privacy-Protective-GAN for Privacy Preserving Face De-Identification

Yifan Wu1, Fan Yang1, Yong Xu2, Senior Member, CCF, ACM, IEEE, and Haibin Ling1, Senior Member, IEEE   

  1. 1 Department of Computer and Information Sciences, Temple University, Philadelphia 19122, U.S.A.;
    2 School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China
  • Received:2018-07-12 Revised:2018-12-20 Online:2019-01-05 Published:2019-01-12
  • About author:Yifan Wu received her B.S. degree in communication engineering from China University of Geosciences, Wuhan, and M.S. degree in computer science from Temple University, Philadelphia, in 2016 and 2017, respectively. She is currently a Ph.D. student in bioengineering at University of Pennsylvania, Philadelphia. Her current research interests are computer vision and medical image processing.
  • Supported by:
    This work was supported by the National Natural Science Foundation of China under Grant No. 61528204, and the National Science Foundation of USA under Grant No. 1350521.

PDF (PC)

976

补充材料

1

在这个图片及影像资源迅速增长并且随处可得的时代，人脸去识别变得越来越至关重要。人脸识别技术的迅速发展，也引起了人们对隐私泄露的担忧。目前的主流人脸去识别框架，大部分是基于"k-same"算法，在有效性及生成图片质量上有待提高。在这篇文章中，我们提出隐私保护对抗生成网络（PP-GAN），结合GAN及新的验证、约束模块，设计用于在给定单帧输入时，生成去识别而保留结构相似性的输出。我们提出的方法不仅优于现有的人脸去识别技术，且提供了结合GAN和先验知识的实用框架。
目的：通过人脸去识别来实现隐私保护，同时通过保持原始图像和生成图像的结构相似性来保留去识别图像的可用性。
创新点：本文提出了PP-GAN来直接优化人脸去识别目标，从而生成图像质量好，去识别有效性高的图像。
方法： PP-GAN，由常规GAN，人脸验证模块和结构相似约束模块构成，通过组合优化，实现最终的去识别生成器。
结论：我们呈现了一个新的人脸去识别框架PP-GAN，可以给定单张人脸图片，生成相应的去识别图片。我们显式地在目标函数中加入了去识别指标，从而保证了隐私保护的有效性，同时，我们希望尽可能地保持输入和生成图像的结构相似性，以最大程度地保留去识别图片的可用性。在实验部分，我们定量分析了提出算法在隐私保护，可用性保留和视觉相似性方面的有效性。

关键词: 人脸去识别, 隐私保护, 图像生成

Abstract: Face de-identification has become increasingly important as the image sources are explosively growing and easily accessible. The advance of new face recognition techniques also arises people's concern regarding the privacy leakage. The mainstream pipelines of face de-identification are mostly based on the k-same framework, which bears critiques of low effectiveness and poor visual quality. In this paper, we propose a new framework called Privacy-Protective-GAN (PP-GAN) that adapts GAN (generative adversarial network) with novel verificator and regulator modules specially designed for the face de-identification problem to ensure generating de-identified output with retained structure similarity according to a single input. We evaluate the proposed approach in terms of privacy protection, utility preservation, and structure similarity. Our approach not only outperforms existing face de-identification techniques but also provides a practical framework of adapting GAN with priors of domain knowledge.

Key words: face de-identification, privacy protection, image synthesis, generative adversarial network (GAN)

[1] Newton E M, Sweeney L, Malin B. Preserving privacy by de-identifying face images. IEEE Transactions on Knowledge and Data Engineering, 2005, 17(2):232-243.
[2] Ribaric S, Ariyaeeinia A, Pavesic N. De-identification for privacy protection in multimedia content:A survey. Signal Processing:Image Communication, 2016, 47:131-151.
[3] Gross R, Airoldi E, Malin B, Sweeney L. Integrating utility into face de-identification. In Proc. the 5th International Conference on Privacy Enhancing Technologies, May 2005, pp.227-242.
[4] Gross R, Sweeney L, de la Torre F, Baker S. Model-based face de-identification. In Proc. the 2006 Conference on Computer Vision and Pattern Recognition, Jun. 2006, Article No. 161.
[5] Gross R, Sweeney L, de La Torre F, Baker S. Semisupervised learning of multi-factor models for face deidentification. In Proc. the 2008 Conference on Computer Vision and Pattern Recognition, Jun. 2008, Article No. 10.
[6] Matthews I, Baker S. Active appearance models revisited. International Journal of Computer Vision, 2004, 60(2):135-164.
[7] Du L, Yi M, Blasch E, Ling H. GARP-face:Balancing privacy protection and utility preservation in face deidentification. In Proc. IEEE International Joint Conference on Biometrics, Sept. 2014, Article No. 67.
[8] Jourabloo A, Yin X, Liu X. Attribute preserved face deidentification. In Proc. IEEE International Conference on Biometrics, May 2015, pp.278-285.
[9] Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, WardeFarley D, Ozair S, Courville A, Bengio Y. Generative adversarial nets. In Proc. Annual Conference on Neural Information Processing Systems, Dec. 2014, pp.2672-2680.
[10] Isola P, Zhu J Y, Zhou T, Efros A A. Image-to-image translation with conditional adversarial networks. In Proc. the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Jul. 2017, pp.5967-5976.
[11] Zhu J Y, Park T, Isola P, Efros A A. Unpaired imageto-image translation using cycle-consistent adversarial networks. In Proc. the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Jul. 2017, pp.2242-2251.
[12] Hadsell R, Chopra S, LeCun Y. Dimensionality reduction by learning an invariant mapping. In Proc. the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Jun. 2006, pp.1735-1742.
[13] Wang Z, Bovik A C, Sheikh H R, Simoncelli E P. Image quality assessment:From error visibility to structural similarity. IEEE Transactions on Image Processing, 2004, 13(4):600-612.
[14] Schroff F, Kalenichenko D, Philbin J. FaceNet:A unified embedding for face recognition and clustering. In Proc. the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2015, pp.815-823.
[15] Zhang K, Zhang Z, Li Z, Qiao Y. Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Processing Letters, 2016, 23(10):1499-1503.
[16] Sun Q, Tewari A, Xu W, Fritz M, Theobalt C, Schiele B. A hybrid model for identity obfuscation by face replacement. In Proc. the 15th European Conference on Computer Vision, Sept. 2018, pp.570-586.
[17] Chen D, Chang Y, Yan R, Yang J. Tools for protecting the privacy of specific individuals in video. EURASIP Journal on Advances in Signal Processing, 2007, 2007(1):Article No. 075427.
[18] Wilber M J, Boult T E. Secure remote matching with privacy:Scrambled support vector vaulted verification (S2V3). In Proc. IEEE Workshop on Applications of Computer Vision, Jan. 2012, pp.169-176.
[19] Chan A B, Liang Z S, Vasconcelos N. Privacy preserving crowd monitoring:Counting people without people models or tracking. In Proc. the 2008 IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2018, Article No. 229.
[20] Sun Q, Ma L, Oh S J, van Gool L, Schiele B, Fritz M. Natural and effective obfuscation by head inpainting. In Proc. the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2018, pp.5050-5059.
[21] Sun Q, Schiele B, Fritz M. A domain based approach to social relation recognition. In Proc. the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Jul. 2017, pp.435-444.
[22] Mirjalili V, Raschka S, Namboodiri A, Ross A. Semiadversarial networks:Convolutional autoencoders for imparting privacy to face images. In Proc. the 2018 International Conference on Biometrics, Feb. 2018 pp.82-89.
[23] Ribaric S, Ariyaeeinia A, Pavesic N. De-identification for privacy protection in multimedia content:A survey. Signal Processing:Image Communication, 2016, 47:131-151.
[24] Gross R, Sweeney L, Cohn J, de la Torre F, Baker S. Face de-identification. In Protecting Privacy in Video Surveillance, Senior A (ed.), Springer, 2009, pp.129-146.
[25] Frome A, Cheung G, Abdulkader A, Zennaro M, Wu B, Bissacco A, Adam H, Neven H, Vincent L. Large-scale privacy protection in Google street view. In Proc. the 12th International Conference on Computer Vision, Sept. 2009, pp.2373-2380.
[26] Sweeney L. k-anonymity:A model for protecting privacy. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 2002, 10(5):557-570.
[27] Brkic K, Sikiric I, Hrkac T, Kalafatic Z. I know that person:Generative full body and face de-identification of people. In Proc. the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Jul. 2017, pp.1319-1328.
[28] Meden B, Mallı R C, Fabijan S, Ekenel H K, Struc V, Peer P. Face deidentification with generative deep neural networks. IET Signal Processing, 2017, 11(9):1046-54.
[29] Meden B, Ziga E, Struc V, Peer P. k-same-net:k-anonymity with generative deep neural networks for face deidentification. Entropy, 2018, 20(1):Article No. 60.
[30] Ioffe S, Szegedy C. Batch normalization:Accelerating deep network training by reducing internal covariate shift. In Proc. the 32nd International Conference on Machine Learning, Jul. 2015, pp.448-456.
[31] Ronneberger O, Fischer P, Brox T. U-net:Convolutional networks for biomedical image segmentation. In Proc. the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention, Oct. 2015 pp.234-241.
[32] Chopra S, Hadsell R, LeCun Y. Learning a similarity metric discriminatively, with application to face verification. In Proc. the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Jun. 2005, pp.539-546.
[33] Sun Y, Chen Y, Wang X, Tang X. Deep learning face representation by joint identification-verification. In Proc. the 2014 Annual Conference on Neural Information Processing Systems, Dec. 2014, pp.1988-1996.
[34] Schroff F, Kalenichenko D, Philbin J. FaceNet:A unified embedding for face recognition and clustering. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2015, pp.815-823.
[35] Parkhi O M, Vedaldi A, Zisserman A. Deep face recognition. In Proc. the 26th British Machine Vision Conference, Sept. 2015, Article No. 6.
[36] Wu X, He R, Sun Z, Tan T. A light CNN for deep face representation with noisy labels. IEEE Transactions on Information Forensics and Security, 2018, 13(11):2884-2896.
[37] Lin M, Chen Q, Yan S. Network in network. arXiv:1312.4400, 2013. https://arxiv.org/pdf/131-2.4400.pdf, Sept. 2018.
[38] Du L, Ling H. Preservative license plate de-identification for privacy protection. In Proc. the 2011 International Conference on Document Analysis and Recognition, Sept. 2011, pp.468-472.
[39] Ricanek K, Tesafaye T. MORPH:A longitudinal image database of normal adult age-progression. In Proc. the 7th International Conference on Automatic Face and Gesture Recognition, Apr. 2006, pp.341-345.
[40] Kingma D P, Ba J. Adam:A method for stochastic optimization. arXiv:1412.6980, 2015. https://arxiv.org/pdf/1412.6980.pdf, Sept. 2018.
[1] Yubin Duan, Guo-Ju Gao, Ming-Jun Xiao, Jie Wu. 网约车平台中基于隐匿区域的乘客位置信息保护机制[J]. 计算机科学技术学报, 2020, 35(3): 629-646.
[2] Chong Wang, Nasro Min-Allah, Bei Guan, Yu-Qi Lin, Jing-Zheng Wu, Yong-Ji Wang. 一种基于反检测指标的虚拟机存储隐蔽信道威胁限制算法[J]. 计算机科学技术学报, 2019, 34(6): 1351-1365.
[3] Lei Cui, Youyang Qu, Mohammad Reza Nosouhi, Shui Yu, Jian-Wei Niu, Gang Xie. 个性化差分隐私保护中基于博弈论的数据可用性提高方法[J]. 计算机科学技术学报, 2019, 34(2): 272-286.
[4] Bao-Kun Zheng, Lie-Huang Zhu, Meng Shen, Feng Gao, Chuan Zhang, Yan-Dong Li, Jin. 基于区块链的可扩展和隐私保护的数据共享[J]. , 2018, 33(3): 557-567.
[5] Yu-Tao Liu, Dong Du, Yu-Bin Xia, Hai-Bo Chen, Bin-Yu Zang, Zhenkai Liang. 基于互不信任双方协作机制的密码管理器[J]. , 2018, 33(1): 98-115.
[6] An Liu, Zhi-Xu Li, Guan-Feng Liu, Kai Zheng, Min Zhang, Qing Li, Xiangliang Zhan. 隐私保护的空间众包任务分配[J]. , 2017, 32(5): 905-918.
[7] Xian-Mang He, Xiaoyang Sean Wang, Member, CCF, ACM, IEEE, Dong Li, Yan-Ni Hao. 半同构泛化:改进同构泛化在云计算中的隐私保护[J]. , 2016, 31(6): 1124-1135.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 《计算机科学技术学报》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持：support@magtech.com.cn
总访问量：